{"id":"https://openalex.org/W7225820865","doi":"https://doi.org/10.5281/zenodo.24124927","title":"Study bias inflates cross-phenotype gene overlaps: a macrocephaly case study","display_name":"Study bias inflates cross-phenotype gene overlaps: a macrocephaly case study","publication_year":2026,"publication_date":"2026-11-11","ids":{"openalex":"https://openalex.org/W7225820865","doi":"https://doi.org/10.5281/zenodo.24124927"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24124927","doi":"https://doi.org/10.5281/zenodo.24124927","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24124927","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.24124927","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5161447180","display_name":"Hafsa Fathima Khajamainudeen","orcid":"https://orcid.org/0009-0007-5168-4050","observed_orcids":["https://orcid.org/0009-0007-5168-4050"]},"institutions":[{"id":"https://openalex.org/I43814544","display_name":"Sathyabama Institute of Science and Technology","ror":"https://ror.org/01defpn95","country_code":"IN","type":"education","lineage":["https://openalex.org/I43814544"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Khajamainudeen, Hafsa Fathima","raw_affiliation_strings":["Sathyabama Institute of Science and Technology"],"raw_orcid":"https://orcid.org/0009-0007-5168-4050","affiliations":[{"raw_affiliation_string":"Sathyabama Institute of Science and Technology","institution_ids":["https://openalex.org/I43814544"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5161447180"],"corresponding_institution_ids":["https://openalex.org/I43814544"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.6470000147819519,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.6470000147819519,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.3285999894142151,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11642","display_name":"Genomics and Rare Diseases","score":0.011300000362098217,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C2781083543","wikidata":"https://www.wikidata.org/wiki/Q635339","display_name":"Macrocephaly","level":2,"score":0.8762000203132629},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.7204999923706055},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.6255999803543091},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.5895000100135803},{"id":"https://openalex.org/C69991583","wikidata":"https://www.wikidata.org/wiki/Q1423575","display_name":"Candidate gene","level":3,"score":0.4876999855041504},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.43790000677108765},{"id":"https://openalex.org/C205778803","wikidata":"https://www.wikidata.org/wiki/Q38404","display_name":"Autism","level":2,"score":0.41280001401901245},{"id":"https://openalex.org/C176671685","wikidata":"https://www.wikidata.org/wiki/Q730600","display_name":"Hypergeometric distribution","level":2,"score":0.396699994802475},{"id":"https://openalex.org/C151810110","wikidata":"https://www.wikidata.org/wiki/Q7307074","display_name":"RefSeq","level":4,"score":0.37130001187324524},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.3693999946117401},{"id":"https://openalex.org/C2987395477","wikidata":"https://www.wikidata.org/wiki/Q135085","display_name":"Gene ontology","level":4,"score":0.36739999055862427},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3361000120639801},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.33390000462532043},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.31839999556541443},{"id":"https://openalex.org/C143589142","wikidata":"https://www.wikidata.org/wiki/Q2617554","display_name":"Loss of heterozygosity","level":4,"score":0.3147999942302704},{"id":"https://openalex.org/C2908923196","wikidata":"https://www.wikidata.org/wiki/Q5205742","display_name":"Gene Annotation","level":4,"score":0.3052000105381012},{"id":"https://openalex.org/C501734568","wikidata":"https://www.wikidata.org/wiki/Q42918","display_name":"Mutation","level":3,"score":0.2897000014781952},{"id":"https://openalex.org/C2776395126","wikidata":"https://www.wikidata.org/wiki/Q431643","display_name":"Microcephaly","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C2776547343","wikidata":"https://www.wikidata.org/wiki/Q24284978","display_name":"Major gene","level":3,"score":0.2824000120162964},{"id":"https://openalex.org/C180754005","wikidata":"https://www.wikidata.org/wiki/Q80726","display_name":"Allele","level":3,"score":0.2702000141143799},{"id":"https://openalex.org/C191988596","wikidata":"https://www.wikidata.org/wiki/Q628374","display_name":"Null hypothesis","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C197077220","wikidata":"https://www.wikidata.org/wiki/Q720988","display_name":"Human genome","level":4,"score":0.2669000029563904},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.26510000228881836},{"id":"https://openalex.org/C37463918","wikidata":"https://www.wikidata.org/wiki/Q387981","display_name":"Allele frequency","level":4,"score":0.26170000433921814},{"id":"https://openalex.org/C68873052","wikidata":"https://www.wikidata.org/wiki/Q349856","display_name":"Genetic variation","level":3,"score":0.2556000053882599}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24124927","doi":"https://doi.org/10.5281/zenodo.24124927","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24124927","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5281/zenodo.24124928","doi":"https://doi.org/10.5281/zenodo.24124928","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24124928","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.5281/zenodo.24124927","doi":"https://doi.org/10.5281/zenodo.24124927","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24124927","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Gene":[0],"sets":[1,97],"drawn":[2],"from":[3,104],"phenotype":[4],"ontologies":[5],"are":[6,55],"widely":[7],"used":[8],"to":[9,35,38,57,142,173,183],"ask":[10],"how":[11,246],"much":[12,247],"two":[13],"conditions":[14],"share":[15],"their":[16,111],"genetic":[17,83],"basis.":[18],"These":[19,235],"comparisons":[20],"rest":[21],"on":[22],"an":[23,157,261],"assumption":[24],"that":[25,29,53,148,238,254],"is":[26,32,258,263],"rarely":[27],"tested:":[28],"a":[30,43,66,81,91,138,255],"gene":[31,96,161,249],"equally":[33,158],"likely":[34],"be":[36,243],"annotated":[37,56,218],"any":[39],"phenotype.":[40],"In":[41],"practice":[42],"small":[44],"number":[45],"of":[46,59,71,80,214],"genes":[47,63,75,205,219],"have":[48,64],"been":[49,251],"studied":[50,74],"so":[51,147,197],"intensively":[52],"they":[54],"hundreds":[58],"phenotypes,":[60,210],"while":[61],"most":[62,216],"only":[65,189],"few":[67],"annotations.":[68],"Shared":[69],"membership":[70],"these":[72],"heavily":[73,217],"can":[76,242],"create":[77],"the":[78,105,115,149,153,168,180,190,215,221],"appearance":[79],"shared":[82,206],"basis":[84],"where":[85],"none":[86],"exists.":[87],"Using":[88],"macrocephaly":[89,123],"as":[90,265],"case":[92],"study,":[93],"I":[94,132],"built":[95],"for":[98],"macrocephaly,":[99],"microcephaly,":[100],"autism":[101],"and":[102,109,179,195,253],"seizure":[103],"Human":[106],"Phenotype":[107],"Ontology":[108],"measured":[110],"pairwise":[112],"overlaps":[113,121],"with":[114,122,226],"standard":[116],"hypergeometric":[117],"test.":[118],"All":[119],"three":[120],"were":[124,223],"strongly":[125],"significant":[126],"(1.5\u20132.2":[127],"fold,":[128,199,231],"p":[129,200,232],"<":[130,201],"1e-4).":[131,202],"then":[133],"retested":[134],"each":[135,143,248],"overlap":[136,154,171,182,192,240,262],"against":[137],"permutation":[139],"null":[140,257],"matched":[141],"gene\u2019s":[144],"annotation":[145],"load,":[146],"comparison":[150],"asks":[151],"whether":[152],"exceeds":[155],"what":[156],"well-studied":[159],"random":[160],"set":[162],"would":[163],"give.":[164],"Under":[165],"this":[166],"test":[167],"macrocephaly\u2013":[169],"microcephaly":[170],"fell":[172],"1.00":[174],"fold":[175,185],"(p":[176,186],"=":[177,187,233],"0.51)":[178],"macrocephaly\u2013autism":[181],"1.07":[184],"0.29);":[188],"macrocephaly\u2013seizure":[191],"remained":[193],"significant,":[194],"modestly":[196],"(1.14":[198],"The":[203],"37":[204],"by":[207,245],"all":[208],"four":[209],"which":[211],"include":[212],"several":[213],"in":[220],"ontology,":[222],"also":[224],"consistent":[225],"study":[227],"bias":[228],"alone":[229],"(1.03":[230],"0.45).":[234],"results":[236],"show":[237],"ontology-based":[239],"statistics":[241],"dominated":[244],"has":[250],"studied,":[252],"study-bias-matched":[256],"needed":[259],"before":[260],"interpreted":[264],"biological.":[266]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-12T00:00:00"}
